Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
first LoRA that actually helped
#9
Quote:[quote]Tried to reproduce it just now. My result was mixed: first run looked bad, second run looked normal. The main thing that moved was latency, not

What worked for me was pretty simple. If you're on vLLM, I'd confirm the version first and then reduce variables until the behavior is obvious. Once you know the plain path works, then add the faster path back in piece by piece.
measure twice, benchmark three times
Reply


Messages In This Thread
first LoRA that actually helped - by batchsize - 10-06-2026, 11:41 AM
Re: first LoRA that actually helped - by llm_wren - 10-15-2026, 05:00 AM
Re: first LoRA that actually helped - by cacheline - 10-15-2026, 04:19 AM

Forum Jump:


Users browsing this thread: 1 Guest(s)